Hybrid convolutional long short‐term memory models for sales forecasting in retail
Journal of Forecasting · 2024-08 · 43 (5) · 1278-1293
DOI: 10.1002/for.3073 ↗At a glance
Journal article in Journal of Forecasting, published online on 2024-02-13. Written by Thais de Castro Moraes and 2 co-authors. Cited 31 times so far (Crossref); 61 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Agency for Science, Technology and Research.
Abstract (original language)
This study proposes novel sales forecasting approaches that merge deep learning methods in a hybrid model. Long short‐term memory (LSTM) is adopted for modeling the temporal characteristics of the data, whereas the convolutional neural network (CNN) focuses on identifying and extracting relevant exogenous information. We propose stacked (S‐CNN‐LSTM) and parallel (P‐CNN‐LSTM) hybrid architectures to understand complex time series data with varying seasonal patterns and multiple products correlations. The performance drivers of both architectures were empirically tested with a real‐world multivariate retail dataset and outperformed when compared with simple neural network architectures and standard autoregressive methods for short and long‐term forecasting horizons. When compared with traditional predictive approaches, the proposed hybrid models reduce the computational complexity while providing flexibility and robustness.
Funding
- Agency for Science, Technology and Research
Cite
APA
Moraes, T. D. C., Yuan, X., & Chew, E. P. (2024). Hybrid convolutional long short‐term memory models for sales forecasting in retail. Journal of Forecasting, 43(5), 1278-1293. https://doi.org/10.1002/for.3073
Vancouver
Moraes TDC, Yuan X, Chew EP. Hybrid convolutional long short‐term memory models for sales forecasting in retail. Journal of Forecasting. 2024;43(5):1278-1293. doi:10.1002/for.3073
BibTeX
@article{Moraes2024,
author = {Moraes, Thais de Castro and Yuan, Xue‐Ming and Chew, Ek Peng},
title = {Hybrid convolutional long short‐term memory models for sales forecasting in retail},
journal = {Journal of Forecasting},
year = {2024},
volume = {43},
number = {5},
pages = {1278--1293},
doi = {10.1002/for.3073}
}
EUVIMED